A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Improved VAE models avoid posterior collapse in text modeling.
Incompatible operations affect Khovanov homology and spectral sequences.
Transformer adapts to graphs with adaptive attention and auto-regressive decoding.
This paper reviews incompatibilities of comonotonic risk measures.
Differentiable sorting and rank normalization are incompatible, with specific conditions for admissibility.
The paper explores the incompatibility between fair privacy, need-to-know, and fairness in classifier outputs.
Defense against backdoor attacks by clustering incompatible data subsets.
New insights into encoder-decoder structures using information measures.
New insights into how encoder-decoder networks generate attention matrices.
Given a distribution of defects on a structured surface, such as those represented by 2-dimensional crystalline materials, liquid crystalline surfaces, and thin sandwiched shells, what is the resulting stress field and the deformed shape? Motivated by this concern, we first classify, and quantify, the translational, ro…
Encoder-decoder networks using convolutional neural network (CNN) architecture have been extensively used in deep learning literatures thanks to its excellent performance for various inverse problems. However, it is still difficult to obtain coherent geometric view why such an architecture gives the desired performance…
The paper uses neural networks to forecast time series data.
Study shows incompatibility of certain scalar curvatures on manifolds.
We discuss several issues regarding material homogeneity and strain compatibility for materially uniform thin elastic shells from the viewpoint of a 3-dimensional theory, with small thickness, as well as a 2-dimensional Cosserat theory. A relationship between inhomogeneity and incompatibility measures under the two des…
For a bounded N-dimensional domain with Lipschitz boundary we extend Korn's first inequality to incompatible tensor fields. For compatible tensor fields our estimate reduces to a non-standard variant of the well known Korn's first inequality. On the other hand, for skew-symmetric tensor fields our new estimate turns to…
We derive a continuum model for incompatible elasticity as a variational limit of a family of discrete nearest-neighbor elastic models. The discrete models are based on discretizations of a smooth Riemannian manifold , endowed with a flat, symmetric connection . The metric deter…
Encoder-decoder GANs architectures (e.g., BiGAN and ALI) seek to add an inference mechanism to the GANs setup, consisting of a small encoder deep net that maps data-points to their succinct encodings. The intuition is that being forced to train an encoder alongside the usual generator forces the system to learn meaning…
A model learns stock trading rules from raw prices using encoder-decoder neural network.
In this paper, we propose a novel neural network model called RNN Encoder-Decoder that consists of two recurrent neural networks (RNN). One RNN encodes a sequence of symbols into a fixed-length vector representation, and the other decodes the representation into another sequence of symbols. The encoder and decoder of t…
Deep learning models have shown state-of-the-art performance in many inverse reconstruction problems. However, it is not well understood what properties of the latent representation may improve the generalization ability of the network. Furthermore, limited models have been presented for inverse reconstructions over ti…
Subspace clustering aims to cluster unlabeled data that lies in a union of low-dimensional linear subspaces. Deep subspace clustering approaches based on auto-encoders have become very popular to solve subspace clustering problems. However, the training of current deep methods converges slowly, which is much less effic…
We present a novel unsupervised deep learning approach that utilizes the encoder-decoder architecture for detecting anomalies in sequential sensor data collected during industrial manufacturing. Our approach is designed not only to detect whether there exists an anomaly at a given time step, but also to predict what wi…
This paper tackles the reduction of redundant repeating generation that is often observed in RNN-based encoder-decoder models. Our basic idea is to jointly estimate the upper-bound frequency of each target vocabulary in the encoder and control the output words based on the estimation in the decoder. Our method shows si…
Study of elastic models in non-Euclidean spaces via Γ-convergence.
The fixed-point index of a homeomorphism of Jordan curves measures the number of fixed-points, with multiplicity, of the extension of the homeomorphism to the full Jordan domains in question. The now-classical Circle Index Lemma says that the fixed-point index of a positive-orientation-preserving homeomorphism of round…
New method shows ignoring morphological graph info improves reinforcement learning performance.
In this paper, we propose a refined multi-stage multi-task training strategy to improve the performance of online attention-based encoder-decoder (AED) models. A three-stage training based on three levels of architectural granularity namely, character encoder, byte pair encoding (BPE) based encoder, and attention decod…
Non-Euclidean, or incompatible elasticity is an elastic theory for pre-stressed materials, which is based on a modeling of the elastic body as a Riemannian manifold. In this paper we derive a dimensionally-reduced model of the so-called membrane limit of a thin incompatible body. By generalizing classical dimension red…
In "extreme" computational imaging that collects extremely undersampled or noisy measurements, obtaining an accurate image within a reasonable computing time is challenging. Incorporating image mapping convolutional neural networks (CNN) into iterative image recovery has great potential to resolve this issue. This pape…
Although neural machine translation with the encoder-decoder framework has achieved great success recently, it still suffers drawbacks of forgetting distant information, which is an inherent disadvantage of recurrent neural network structure, and disregarding relationship between source words during encoding step. Wher…
Memory-augmented neural networks (MANNs) have been shown to outperform other recurrent neural network architectures on a series of artificial sequence learning tasks, yet they have had limited application to real-world tasks. We evaluate direct application of Neural Turing Machines (NTM) and Differentiable Neural Compu…
Image compression is an essential approach for decreasing the size in bytes of the image without deteriorating the quality of it. Typically, classic algorithms are used but recently deep-learning has been successfully applied. In this work, is presented a deep super-resolution work-flow for image compression that maps …
The presence of noise is common in signal processing regardless the signal type. Deep neural networks have shown good performance in noise removal, especially on the image domain. In this work, we consider deep neural networks as a denoising tool where our focus is on one dimensional signals. We introduce an encoder-de…
Cincer cleans both new and past data by identifying and relabeling suspicious and counter-examples.
Encoder-decoder based sequence-to-sequence models have demonstrated state-of-the-art results in end-to-end automatic speech recognition (ASR). Recently, the transformer architecture, which uses self-attention to model temporal context information, has been shown to achieve significantly lower word error rates (WERs) co…
Study efficient neural operator learning using variation spaces.
Study clusters bank customers using LSTM and DTW.
This work extends elasticity theory to curved spaces, solving stress potentials.
In this paper, we compare different types of Recurrent Neural Network (RNN) Encoder-Decoders in anomaly detection viewpoint. We focused on finding the model that can learn the same data more effectively. We compared multiple models under the same conditions, such as the number of parameters, optimizer, and learning rat…
We develop a functional encoder-decoder approach to supervised meta-learning, where labeled data is encoded into an infinite-dimensional functional representation rather than a finite-dimensional one. Furthermore, rather than directly producing the representation, we learn a neural update rule resembling functional gra…
Image denoising is always a challenging task in the field of computer vision and image processing. In this paper, we have proposed an encoder-decoder model with direct attention, which is capable of denoising and reconstruct highly corrupted images. Our model consists of an encoder and a decoder, where the encoder is a…
In this paper, we propose a dictionary update method for Nonnegative Matrix Factorization (NMF) with high dimensional data in a spectral conversion (SC) task. Voice conversion has been widely studied due to its potential applications such as personalized speech synthesis and speech enhancement. Exemplar-based NMF (ENMF…
New methods improve integration of external LMs with AED models.
We study the calibration of several state of the art neural machine translation(NMT) systems built on attention-based encoder-decoder models. For structured outputs like in NMT, calibration is important not just for reliable confidence with predictions, but also for proper functioning of beam-search inference. We show …
A novel capsule network model improves surrogate modeling and uncertainty quantification from sparse data.
We study the growth of the rank of subgroups of finite index in residually finite groups, by relating it to the notion of cost. As a by-product, we show that the `Rank vs. Heegaard genus' conjecture on hyperbolic 3-manifolds is incompatible with the `Fixed Price problem' in topological dynamics.
Capsule network has shown various advantages over convolutional neural network (CNN). It keeps more precise spatial information than CNN and uses equivariance instead of invariance during inference and highly potential to be a new effective tool for visual tasks. However, the current capsule networks have incompatible …
A new machine learning method for Bayesian inverse problems in function spaces.